Abstract
We recently proposed a recurrent neural network model for the development of dynamic neural fields [1]. The learning regime incorporates homeostatic processes, such that the network is able to self-organize and maintain a stable operation mode even in face of experience-driven changes in synaptic strengths. However, the learned mappings do not necessarily have to be topology preserving. Here we extend our model by incorporating another mechanism which changes the positions of neurons in the output space. This algorithm operates with a purely local objective function of minimizing the wiring length and runs in parallel to the above mentioned learning process. We experimentally show that the incorporation of this additional mechanism leads to a significant decrease in topological defects and further enhances the quality of the learned mappings. Additionally, the proposed algorithm is not limited to our network model; rather it can be applied to any type of self-organizing maps.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Gläser, C., Joublin, F., Goerick, C.: Homeostatic development of dynamic neural fields. In: Proc. International Conference on Development and Learning (2008)
Kangas, J.: Utilizing the similarity preserving properties of self-organizing maps in vector quantization of images. In: Proc. International Conference on Neural Networks, vol. 4, pp. 2081–2084 (1995)
Vörös, T., Keresztényi, Z., Fazekas, C., Laczkó, J.: Computer aided interactive remote diagnosis using self-organizing maps. In: Proc. 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 5, pp. 3190–3193 (2004)
Alhoniemi, E., Hollmén, J., Simula, O., Vesanto, J.: Process monitoring and modeling using the self-organizing map. Integrated Computer-Aided Engineering 6(1), 3–14 (1999)
Herrmann, M.: Self-organizing feature maps with self-organizing neighborhood widths. In: Proc. International Conference on Neural Networks, pp. 2998–3003 (1995)
Phaf, R., Den Dulk, P., Tijsseling, A., Lebert, E.: Novelty-dependent learning and topological mapping. Connection Science 13(4), 293–321 (2001)
Kirk, J.S., Zurada, J.M.: Algorithms for improved topology preservation in self-organizingmaps. In: Proc. International Conference on Systems, Man, and Cybernetics, vol. 3, pp. 396–400 (1999)
Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernetics 27, 77–87 (1977)
Williams, S., Stuart, G.: Role of dendritic synapse location in the control of action potential output. Trends in Neuroscience 26(3), 147–154 (2003)
Kiviluoto, K.: Topology preservation in self-organizing maps. In: Proc. International Conference on Neural Networks, vol. 1, pp. 294–299 (1996)
Kirk, J.S., Zurada, J.M.: A two-stage algorithm for improved topography preservation in self-organizing maps. In: Proc. International Conference on Systems, Man, and Cybernetics, vol. 4, pp. 2527–2532 (2000)
Villmann, T., Der, R., Herrmann, M., Martinetz, T.M.: Topology preservation in self-organizing feature maps: Exact definition and measurement. IEEE Transactions on Neural Networks 8(2), 256–266 (1997)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69 (1982)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gläser, C., Joublin, F., Goerick, C. (2008). Enhancing Topology Preservation during Neural Field Development Via Wiring Length Minimization. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_61
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_61
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)